paper-with-me

홈 › Papers

Tackling Graph Oversquashing by Global and Local Non-Dissipativity

2024-05-02 · Alessio Gravina, Moshe Eliasof, Claudio Gallicchio, Davide Bacciu, Carola-Bibiane Schönlieb

A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes. Oversquashing is attributed to the exponential decay in information transmission as node distances increase. This paper introduces a novel perspective to address oversquashing, leveraging properties of global and local non-dissipativity, that enable the maintenance of a constant information flow rate. Namely, we present SWAN, a uniquely parameterized model GNN with antisymmetry both in space and weight domains, as a means to obtain non-dissipativity. Our theoretical analysis asserts that by achieving these properties, SWAN offers an enhanced ability to transmit information over extended distances. Empirical evaluations on synthetic and real-world benchmarks that emphasize long-range interactions validate the theoretical understanding of SWAN, and its ability to mitigate oversquashing.

📄 PDF Abstract BibTeX arXiv:2405.01009

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Exponential Decay Exponential Decay is a learning rate schedule where we decay the learning rate with more iterations using an exponential function: $$ \text{lr} =…

Similar Papers 제목 키워드 기반

On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems

2025-04-11 · AAAI 2025 4 · Alessio Gravina, Moshe Eliasof, Claudio Gallicchio, Davide Bacciu 외

A common problem in Message-Passing Neural Networks is oversquashing -- the limited ability to facilitate effective information flow between distant nodes. Oversquashing is attributed to the exponential decay in informat…

Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models

2025-10-20 · Li Sun, Zhenhao Huang, Ming Zhang, Philip S. Yu arxiv

Message Passing Neural Networks (MPNNs) is the building block of graph foundation models, but fundamentally suffer from oversmoothing and oversquashing. There has recently been a surge of interest in fixing both issues. …

Oversquashing in GNNs through the lens of information contraction and graph expansion

2022-08-06 · Pradeep Kr. Banerjee, Kedar Karhadkar, Yu Guang Wang, Uri Alon 외

The quality of signal propagation in message-passing graph neural networks (GNNs) strongly influences their expressivity as has been observed in recent works. In particular, for prediction tasks relying on long-range int…

graph construction

Expander Graph Propagation

2022-10-06 · Andreea Deac, Marc Lackenby, Petar Veličković

Deploying graph neural networks (GNNs) on whole-graph classification or regression tasks is known to be challenging: it often requires computing node features that are mindful of both local interactions in their neighbou…

Graph ClassificationGraph Representation LearningNavigateRepresentation Learning

Cross-attentive Cohesive Subgraph Embedding to Mitigate Oversquashing in GNNs

2026-03-29 · Tanvir Hossain, Muhammad Ifte Khairul Islam, Lilia Chebbah, Charles Fanning 외 arxiv

Graph neural networks (GNNs) have achieved strong performance across various real-world domains. Nevertheless, they suffer from oversquashing, where long-range information is distorted as it is compressed through limited…

Graph Learning